INDEX

Explanations

instances where something is being identified or highlighted

oai_token-act-pair · gpt-4o-mini Triggered by @bot

"point" or "pointing"

np_acts-logits-general · gemini-2.0-flash

point to or out

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

PRWEB

-0.66

 FetchType

-0.65

 SafeMath

-0.62

 viewDidLoad

-0.59

FetchType

-0.58

 coaster

-0.58

ynh

-0.57

 MonoBehaviour

-0.57

beats

-0.57

LikeLike

-0.56

POSITIVE LOGITS

 pointed

1.00

 pointing

0.96

pointed

0.76

 apont

0.76

 pointers

0.71

pointing

0.68

 apon

0.62

 weisen

0.61

 allude

0.61

zeigen

0.61

Activations Density 0.106%

instances where something is being identified or highlighted

"point" or "pointing"

point to or out

No Comments

No Known Activations